Semi-Markov Switching Vector Autoregressive Model-Based Anomaly Detection in Aviation Systems

  title={Semi-Markov Switching Vector Autoregressive Model-Based Anomaly Detection in Aviation Systems},
  author={Igor Melnyk and Bryan L. Matthews and Hamed Valizadegan and Arindam Banerjee and Nikunj C. Oza},
  journal={Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining},
  • Igor MelnykB. Matthews N. Oza
  • Published 21 February 2016
  • Computer Science
  • Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
In this work we consider the problem of anomaly detection in heterogeneous, multivariate, variable-length time series datasets. Our focus is on the aviation safety domain, where data objects are flights and time series are sensor readings and pilot switches. In this context the goal is to detect anomalous flight segments, due to mechanical, environmental, or human factors in order to identifying operationally significant events and highlight potential safety risks. For this purpose, we propose… 

Figures and Tables from this paper

Identifying Instantaneous Anomalies in General Aviation Operations

A novel method of identifying instantaneous anomalies for retrospective safety analysis using energy-based metrics is proposed and is compared with traditional methods of safety assessment (exceedance detection).

Hybrid Machine Learning–Statistical Method for Anomaly Detection in Flight Data

This research took advantage of machine learning techniques to recognize patterns in large datasets by implementing the local outlier factor (LOF) and demonstrated that LOF quantifies the degree of outlier-ness of an outlier rather than binary categorizing a point into inlier or outlier, as in the case of clustering algorithms.

Recent Advances in Anomaly Detection Methods Applied to Aviation

The state-of-the-art of data-driven anomaly detection techniques and their application to the aviation domain are reviewed, ranging from the identification of significant operational events in air traffic operations to the prediction of potential aviation system failures for predictive maintenance.

Data-driven system health monitoring technique using autoencoder for the safety management of commercial aircraft

The results show that the proposed aircraft upset detector technique can enhance pilots’ situational awareness by providing early safety alert for more effective flight safety management and real-time detection of upset precursors in flight datasets.

A Three-Dimensional ResNet and Transformer-Based Approach to Anomaly Detection in Multivariate Temporal–Spatial Data

TDRT, a three-dimensional ResNet and transformer-based anomaly detection method that can automatically learn the multi-dimensional features of temporal–spatial data to improve the accuracy of anomaly detection, is proposed.

An Incremental Clustering Method for Anomaly Detection in Flight Data

Application of Machine Learning Techniques to Parameter Selection for Flight Risk Identification

A step-by-step methodology is proposed to down-select a reduced set of parameters that can be used for safety analysis on data from the approach phase of a representative single-aisle aircraft to demonstrate its application and robustness across heterogeneous data sets.

An Adaptive Online Learning Model for Flight Data Cluster Analysis

A reinforcement learning method to identify common patterns in flight data via cluster analysis and update its clusters as new data come in and uses online (recursive) expectation-maximization (EM) algorithm to update clustering results over time.

Identifying Anomalies in past en-route Trajectories with Clustering and Anomaly Detection Methods

This paper presents a framework to identify and characterise anomalies in past en-route Mode S trajectories, which combines a trajectory-clustering method to obtain the main flows in an airspace with autoencoding artificial neural networks to perform anomaly detection in flown trajectories.



Multiple kernel learning for heterogeneous anomaly detection: algorithm and aviation safety case study

This paper discusses a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets.

Comparison of algorithms for anomaly detection in flight Recorder data of airline operations

Two data-driven anomaly detection algorithms are compared and the two datadriven methods are contrasted with the traditional flight data analysis method Exceedance Detection, a Flight Operational Quality Assurance analysis tool widely used in the airline industry.

Analysis of Flight Data Using Clustering Techniques for Detecting Abnormal Operations

The new method, enabled by data from the flight data recorder, applies clustering techniques to detect abnormal flights of unique data patterns and can support domain experts in detecting anomalies and associated risks from routine airline operations.

Anomaly Detection and Diagnosis Algorithms for Discrete Symbol Sequences with Applications to Airline Safety

We present a set of novel algorithms which we call sequenceMiner that detect and characterize anomalies in large sets of high-dimensional symbol sequences that arise from recordings of switch sensors

Markov-switching autoregressive models for wind time series

New Introduction to Multiple Time Series Analysis

This reference work and graduate level textbook considers a wide range of models and methods for analyzing and forecasting multiple time series. The models covered include vector autoregressive,

Automatic outlier detection for time series: an application to sensor data

Two variations of a method that uses the median from a neighborhood of a data point and a threshold value to compare the difference between the median and the observed data value are proposed.

Activity recognition and abnormality detection with the switching hidden semi-Markov model

The switching hidden semi-markov model (S-HSMM) is introduced, a two-layered extension of thehidden semi-Markov model for the modeling task and an effective scheme to detect abnormality without the need for training on abnormal data is proposed.

Variational Learning for Switching State-Space Models

A new statistical model for time series that iteratively segments data into regimes with approximately linear dynamics and learns the parameters of each of these linear regimes is introduced and the results suggest that variational approximations are a viable method for inference and learning in switching state-space models.

Modeling flat stretches, bursts, and outliers in time series using mixture transition distribution models

The class of mixture transition distribution (MTD) time series models is extended to general non-Gaussian time series and the stationarity and autocorrelation properties of the models are derived.